All Dev Resources
3155 resources total
EvoPolicyGym
★ 68A benchmark for evaluating autonomous policy evolution in interactive environments.
SurveilBench
★ 68Dataset for evaluating agentic surveillance capabilities across AI models.
PEGE + DDB
★ 68Policy-Embedded Graph Expansion and Dynamics-Driven Branching for HIV testing optimization.
BranchPoint-Latent
★ 68A zero-replay debugger for identifying causally decisive events in multi-agent LLM traces.
OVI Algorithm
★ 65Interactive on-policy imitation learning algorithm for statistical efficiency.
Superblocks
★ 65A low-code internal tool builder that enables 'vibe-coding' and app/model decoupling.
MGLP
★ 65Implementation of Multi-Granularity Position Embedding of Graphs via Granular-Ball.
Video_Attribution
★ 65A training-free AI-generated video attribution and detection framework.
MASC
★ 65Metaphorical Algorithmic Steering for Code Generation framework for eliciting low-efficiency code.
LSR-Synth
★ 65A benchmark for scientific equation discovery that mitigates training corpus memorization.
ANCHOR
★ 65A controlled synthetic audit for measuring persona enactment and trajectory recall in AI companions.
GenCDSR
★ 65Generative framework for cross-domain sequential recommendation reducing inference latency.
ZimaOS
★ 65A beginner-friendly OS for home servers with one-click Docker app installation.
NZBDAV
★ 65Usenet streaming tool to reduce HDD storage requirements
OPAB
★ 65A method for detecting Outcome Performativity using prediction intervention A/B testing.
Investigation into photometric augmentations for improving OOD generalization in skin lesion classifiers.
FakeIDet3-DB
★ 65Comprehensive database of digital manipulations on real government-issued IDs for forensic training.
THV-UCB
★ 65An optimistic algorithm for Top-k Pareto Bandits with hypervolume regret bounds.
Mail and Parcels
★ 65A self-hosted package tracking application.
Fluxer
★ 65An open-source AI-powered video creation and streaming platform